English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pre-trained contextualized language models (PrLMs) have led to strongperformance gains in downstream natural language understanding tasks. However,PrLMs can still be easily fooled by adversarial word substitution, which is oneof the most challenging textual adversarial attack methods. Existing defenceapproaches suffer from notable performance loss and complexities. Thus, thispaper presents a compact and performance-preserved framework, Anomaly Detectionwith Frequency-Aware Randomization (ADFAR). In detail, we design an auxiliaryanomaly detection classifier and adopt a multi-task learning procedure, bywhich PrLMs are able to distinguish adversarial input samples. Then, in orderto defend adversarial word substitution, a frequency-aware randomizationprocess is applied to those recognized adversarial input samples. Empiricalresults show that ADFAR significantly outperforms those newly proposed defensemethods over various tasks with much higher inference speed. Remarkably, ADFARdoes not impair the overall performance of PrLMs. The code is available athttps://github.com/LilyNLP/ADFAR

Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice